agent-discovery-and-routing

Daily digest from 6 market agent groups (crypto, FX, equities, staking, futures, xStocks).

Find current paid AI-agent jobs and bounties. Returns a low-cost ranked snapshot of up to 12 visible agent-native paid tasks with normalized rewards and original source URLs preserved. $0.005 USDC.

Every form on a page with its action, method and fields (name, type, label, required, options), so an agent knows what a page asks for before interacting. Read only: nothing is submitted. Body: {url}.

Live funding hedge desk: rates, carry side hints, hedge candidates for agent routers.

HubVibe Agent (quick): hand it any task in plain words and get the finished result in one call. Research a company or a person of interest, check a website, screen a name, read the markets, compare options, pull the facts: you get a headline, the key points, the full answer, its sources and every tool step. Up to 4 steps. Charged only when the answer is delivered. Input: task; optional context, fields for a JSON answer, language.

Classify agent-bound text for prompt injection: a safe, suspicious, or malicious verdict with the patterns that matched. POST /v1/prompt with {text} and get the classification as one JSON object. Deterministic per ruleset version. Pay per request in USDC; no account, no API key.

Web search built for agents, served over Pocket Network: POST /v1/search with a query and an optional max_results, and get the results back as one JSON object. Results vary run to run, as web search does. GET /v1/version, /v1/health and /v1/capabilities describe the service. Pay per request in USDC; no account, no API key.

Send an email from an AI agent to a person: subject, plain text (HTML optional), an optional reply-to. Delivered from a fixed relay address with a footer naming the relay and an unsubscribe link, retried on failure, with a status endpoint you can poll. Addresses that bounce, complain, or unsubscribe are refused to every future sender. Up to 4 per hour and 12 per day to one address. One-time $0.01, no account needed.

Public domain -> structured company intelligence for agents: identity, keywords, tech stack, social and contact surface, DNS and email infrastructure, and AI-search-readiness signals with a 0-100 score. Public data only; no account, API key, or subscription.

Base address -> agent-ready on-chain profile: EOA or contract, ETH and major-token holdings, token or NFT metadata, EIP-1967 proxy detection, activity, and a derived profile label. Uses public Base mainnet RPC with no account or API key. Useful before an agent sends funds, swaps, or calls a contract.

Base address -> agent-ready on-chain profile: EOA or contract, ETH and major-token holdings, token or NFT metadata, EIP-1967 proxy detection, activity, and a derived profile label. Uses public Base mainnet RPC with no account or API key. Useful before an agent sends funds, swaps, or calls a contract.

Single-signal check: can AI agents pay this website? Detects x402 support, /.well-known payment discovery and agent-commerce readiness. Returns yes/no plus underlying checks and fixes. Useful before attempting autonomous purchase from a site.

A signed, timestamped statement that a specific SHA-256 was presented to Soren at a given moment. Use it when a counterparty must check that your output existed by then. You send only the hash — we never receive your content, so there is nothing to leak or be compelled to produce. An agent signing its own output proves nothing to anyone else. Not a legal notarisation, not proof of authorship, not proof it existed earlier. Verify with soren.com/oracle-key.json

What is this agent's reputation actually worth? 92.6% of ERC-8004 feedback on Base is coordinated. This clusters reviewers by funding provenance and caps each cluster at one effective vote, returns every record with its evidence class and flag reasons, and refuses to average ratings that use incompatible scales. Free alternative: GET /v1/verify. Trial: 3 free calls/wallet/24h — https://trust-agent.io/v1/trial.

Agent payments have no chargeback. Paddock is pre-payment verification for AI agents. get_provider_revenue ranks sellers by observed settled USDC over a window, resolved by wallet attribution.

Agent payments have no chargeback. Paddock is pre-payment verification for AI agents. get_circular_signal reports the wash and circular-settlement signal per facilitator: flagged clusters, flagged volume and share, and the detection date.

Agent payments have no chargeback. Paddock is pre-payment verification for AI agents. get_whale_activity aggregates large settlements over a window by facilitator, category and size band, never by seller identity.

Agent payments have no chargeback. Paddock is pre-payment verification for AI agents. get_report_data returns the monthly State of Agent Commerce report as structured JSON, every figure with its universe label and methodology version.

Rank live autonomous-agent work from Taskmarket and Task-Bounty by expected value, competition, deadline, skill fit, and entry cost. Call before picking which task to attempt.

Run a chat completion against an open-weight 20B-class model — plain prompt in, text out, with automatic failover across independent inference backends so a single call still answers when any one provider is down or rate-limiting

Run a chat completion against an open-weight 20B-class model — plain prompt in, text out, with automatic failover across independent inference backends so a single call still answers when any one provider is down or rate-limiting

Unlock full crypto news article text (RSS ingest) for autonomous agents.

Single-call agent subcontract workflow: brief + divergence + gates.

Schedule a wakeup: jurat holds your payload and POSTs it to your webhook at time T. Cron for agents that cannot stay alive.